Controlled Multi-source Mapping of Lunar South Polar Regions via Combined Bundle Adjustment

Construction of Control Network for Multi-temporal LRO NAC Images Based on Matching of Lunar Impact Craters

Abstract. The Lunar South Pole (LSP) has extreme illumination, extensive shadows and weak surface texture, which greatly challenge high-precision mapping and render conventional image matching algorithms ineffective for control network construction. To solve this problem, this paper proposes a multi-temporal LRO NAC image control network construction method based on impact crater matching, leveraging their morphological stability and spatial consistency. A manually annotated 1 m/pixel LRO NAC dataset was used to train YOLOv8 for accurate crater parameter extraction. A virtual feature point matching algorithm was developed, which builds crater descriptors by fusing geometric attributes and neighborhood topology, and achieves reliable matching via multi-attribute similarity and bidirectional verification. Secondary NCC refinement was applied to large craters to improve tie point accuracy. Finally, tie points were mapped back to original images for control network construction and bundle adjustment. Comparative experiments on 94 LRO NAC images near 88.5°S (2298 pairs) with SIFT and SuperPoint showed that the proposed method generated ~10,000 stable tie points per pair, with only 45 pairs lacking valid tie points—far fewer than the comparison algorithms. A large-area control network built from 1,847 images yielded 2,219,604 tie points. After bundle adjustment, the unit weight standard error was 0.67, average image RMS 0.83 pixels, maximum below 2 pixels. The resulting DOM and DEM products had excellent quality. This method effectively solves the LSP tie point matching problem and supports high-precision lunar polar topographic mapping.

Bundle-Adjusted Initialization for Efficient Earth Observation Gaussian Splatting

Abstract. Satellite imagery offers a distinct advantage in Earth observation by providing expansive coverage and enabling the monitoring of inaccessible regions without physical on-site intervention, serving as a significantly more cost-effective and scalable alternative to traditional aerial or ground-based surveys. The task of 3D reconstruction from multi-view satellite images has therefore been a pivotal point of research at the intersection of photogrammetry and remote sensing. Recently, novel-view synthesis techniques such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have accelerated the accuracy and speed of topographic modeling. Among these, Earth Observation Gaussian Splatting (EOGS) has emerged as a state-of-the-art approach by adapting 3DGS to handle the unique geometric and radiometric characteristics of satellite data, including Rational Polynomial Coefficients (RPCs) and varying solar conditions. However, the standard EOGS pipeline relies on stochastic initialization, where Gaussians are distributed uniformly within a volumetric bounding box, leading to high computational overhead and dependency on aggressive pruning that can inadvertently remove critical geometric features, particularly in areas with complex urban structures. To address these limitations, we propose Bundle-Adjusted Initialization for Earth Observation Gaussian Splatting, which leverages sparse point clouds from bundle adjustment as geometric priors for Gaussian initialization. Combined with an adaptive densification strategy, our method achieves faster convergence and improved DSM accuracy on the DFC2019 dataset compared to the EOGS baseline.

MCCR: Multi-scale cross-modal cascade registration method for water surface scenes

Multimodal-Multiresolution Foundation Model for Lunar Remote Sensing

We present a multimodal foundation model for lunar remote sensing, pretrained from scratch on SomBench, a geographically partitioned corpus of nearly two million co-registered tile bundles spanning 11 modalities at two spatial scales (1 m/pixel and 100 m/pixel). The model adapts the TerraMind masked-token architecture with two lunar-specific extensions: acquisition geometry is provided as explicit context, and meter- and hundred-meter-scale tiles are trained jointly so that a single set of weights covers both resolutions. FlexiViT patch embeddings allow adaptation to different patch sizes without retraining, while modality-wise inputs enable flexible multimodal fine-tuning. Qualitative generation experiments suggest the model learns meaningful cross-modal correspondences, including terrain derivatives from elevation and illumination-consistent reflectance from geometry. We evaluate on four benchmarks: crater detection at WAC and NAC scales, irregular mare patch (IMP) segmentation, and polar ice prospectivity regression. Across tasks, the pretrained model matches or outperforms ImageNet-pretrained baselines and an architecturally identical random-init control. On multimodal ice prospectivity regression, pretrained variants achieve the best results, while the random-init model outperforms most baselines, suggesting gains arise from both the architecture and pretraining. Label efficiency is notable for WAC crater detection, where the pretrained model trained on 50% of the data exceeds the strongest ImageNet baseline trained on the full dataset. Among adaptation strategies, LoRA matches or surpasses full fine-tuning on crater detection and IMP segmentation while using far fewer trainable parameters, whereas full fine-tuning performs best for ice prospectivity regression. We release the pretrained checkpoint, benchmark datasets, and fine-tuning code to support reproducible lunar AI research.

PriSAR: 3D Geometric-Prior-Guided Diffusion for Parameter-Controlled SAR Image Generation

The results support the conclusion that a lightweight 3D geometric prior improves viewpoint adherence for controllable SAR generation; it is intended as generation guidance rather than high-fidelity electromagnetic construction.

Global Block Adjustment for Mosaicked Stereoscopic Satellite Imagery

The results highlight that careful parameterization — combining observation weighting, n-tuple point filtering, and per-satellite sensor refinement — is key to producing accurate, geometrically consistent large-scalemosaics from bi-satellite stereo imagery.